הפקולטה להנדסה ע"ש איבי ואלדר פליישמן

EE Seminar: Visual Perception through Hyper Graphs

~~(The talk will be given in English)

Speaker: Prof. Nikos Paragios
CentraleSupelec, Inria, University of Paris-Saclay, http://cvn.ecp.fr/personnel/nikos/

Wednesday, May 4th, 2016
15:00 - 16:00
Room 011, Kitot Bldg., Faculty of Engineering

Visual Perception through Hyper Graphs

Abstract
Computational vision, visual computing and biomedical image analysis have made tremendous progress of the past decade. This is mostly due the development of efficient learning and inference algorithms which allow better and richer modeling of visual perception tasks.
Hyper-Graph representations are among the most prominent tools to address such perception through the casting of perception as a graph optimization problem. In this talk, we briefly introduce the interest of such representations, discuss their strength and limitations, provide appropriate strategies for their inference learning and present their application to address a variety of problems of visual computing.

Bio: Nikos Paragios is professor of Applied Mathematics and Computer Science and director of the Center for Visual Computing of CentraleSupelec. Prior to that he was professor/research scientist (2004-2005, 2011-2013)at the Ecole Nationale de Ponts et Chaussees, affiliated with Siemens Corporate Research (Princeton, NJ, 1999-2004) as a project manager, senior research scientist and research scientist. In 2002 he was an adjunct professor at Rutgers University and in 2004 at New York University. N. Paragios was a visiting professor at Yale (2007) and at University of Houston (2009). Professor Paragios is an IEEE Fellow, has co-edited four books, published more than two hundred papers in the most prestigious journals and conferences of medical imaging and computer vision (DBLP server), and holds twenty one US patents. His work has approx 15,750 citations according to Google Scholar and his H-number (03/2016) is 60. He is the Editor in Chief of the Computer Vision and Image Understanding Journal and serves as a member of the editorial board for the Medical Image Analysis Journal (MedIA) and the SIAM Journal in Imaging Sciences (SIIMS). He as served as an associate/area editor/member of the editorial board for the IEEE Transactions on
Pattern Analysis and Machine Intelligence (PAMI), the Computer Vision and Image Understanding Journal (CVIU), the International Journal of Computer Vision (IJCV) and the Journal of Mathematical Imaging and Vision (JMIV) while he was one of the program chairs of the 11th European Conference in Computer Vision (ECCV'10, Heraklion, Crete) and serves regularly at the conference boards of the most prestigious events of his fields (ICCV, CVPR, ECCV, MICCAI). Professor Paragios is member of the scientific council of SAFRAN conglomerate.

04 במאי 2016, 15:00

חדר 011, בניין כיתות-חשמל

טקס רוזנברג

10 באפריל 2016, 14:00

Departmental Seminar Material Sciences and Engineering

Development of routine for solution of alluminide`s structure basing on electron diffraction data

Prof. Louisa Meshi

Department of Materials Engineering and Ilse Katz Institute for Nanosized Science

and Technology, Ben Gurion University of the Negev, Beer-Sheva

13 באפריל 2016, 16:00

Room 103, Engineering Class (Kitot) Building

Departmental Seminar Material Sciences and Engineering

Development of routine for solution of alluminide`s structure basing on electron diffraction data

סמינר מחלקתי Luigi Cavaleri

13 באפריל 2016, 15:00

וולפסון 206

EE Seminar: Subspace polynomials, cyclic subspace codes, and list-decoding of Gabidulin codes

~~(The talk will be given in English)

Speaker: Netanel Raviv
Computer Science Department, Technion

Monday, April 18th, 2016
15:00 - 16:00
Room 011, Kitot Bldg., Faculty of Engineering

Subspace polynomials, cyclic subspace codes, and list-decoding of Gabidulin codes

Abstract
Subspace codes have received an increasing interest recently due to their application in error correction for random network coding. In particular, cyclic subspace codes are possible candidates for large codes with efficient encoding and decoding algorithms. We introduce a new way of representing subspace codes by a class of polynomials called subspace polynomials. We present some constructions of such codes which are cyclic and analyze their parameters.

In addition, the subspace polynomials from one of these constructions is used to show the limits of list decoding of Gabidulin codes, which may be seen as the rank-metric equivalent of Reed-Solomon codes. Our results show that unlike Reed-Solomon codes, there exists certain Gabidulin codes that cannot be list decoded efficiently beyond the unique decoding radius.

Bio: Netanel Raviv received a B.Sc. from the department of mathematics and an M.Sc. from the department of Computer Science at the Technion at 2010 and 2013, respectively. He is now a Doctoral student at the department of Computer Science at the Technion. He is an awardee of the IBM Ph.D. fellowship for the academic year of 2015-2016, and the Aharon and Ephraim Katzir study grant for 2015. His research interests include coding for distributed storage systems, algebraic coding theory, network coding, and algebraic structures.

18 באפריל 2016, 15:00

חדר 011, בניין כיתות-חשמל

EE Seminar: On the Stability of Deep Networks and its Relationship with Compressed Sensing and Metric Learning

~~
Speaker: Dr. Raja Giryes
EE, Tel Aviv University

Monday, April 11th, 2016
15:00 - 16:00
Room 011, Kitot Bldg., Faculty of Engineering

On the Stability of Deep Networks and its Relationship with Compressed Sensing and Metric Learning

Abstract
This lecture will address the fundamental question: What are deep neural networks doing to metrics in the data? We know that two important properties of a classification machinery are: (i) the system preserves the important information of the input data; (ii) the training examples convey information for unseen data; and (iii) the system is able to treat differently points from different classes. We show that these fundamental properties are inherited by the architecture of deep neural networks. We formally prove that these networks with random Gaussian weights perform a distance-preserving embedding of the data, with a special treatment for in-class and out-of-class data. Similar points at the input of the network are likely to have the same output. The theoretical analysis of deep networks presented exploits tools used in the compressed sensing and dictionary learning literature, thereby making a formal connection between these important topics. The derived results allow drawing conclusions on the metric learning properties of the network and their relation to its structure; and provide bounds on the required size of the training set such that the training examples would represent faithfully the unseen data. The results are validated with state-of-the-art trained networks.

Bio:
Raja Giryes is a faculty member in the school of electrical engineering at Tel Aviv University. His research interests lie at the intersection between signal and image processing and machine learning, and in particular, in deep learning, inverse problems, sparse representations, and signal and image modeling. More details in web.eng.tau.ac.il/~raja

11 באפריל 2016, 15:00

חדר 011, בניין כיתות-חשמל

סמינר מחלקתי Prof. Imberger

18 במאי 2016, 15:00

וולפסון 206

EE Seminar: Non-smooth manifold optimization with applications to machine learning and pattern recognition

~~(The talk will be given in English)

Speaker: Prof. Michael Bronstein
University of Lugano, Switzerland / Perceptual Computing, Intel, Israel RAS, Moscow, Russia

Sunday, April 3rd, 2016
14:00 - 15:00
Room 011, Kitot Bldg., Faculty of Engineering

Non-smooth manifold optimization with applications to machine learning and pattern recognition

Abstract
Numerous problems in machine learning are formulated as optimization with manifold constraints, i.e., where the variables are restricted to a smooth submanifold of the search space. For example, optimization on the Grassman manifold comes up in multi-view clustering and matrix completion; Stiefel manifolds arise in eigenvalue-, assignment-, and Procrustes problems, compressed sensing, shape correspondence, manifold learning, sensor localization, structural biology, and structure from motion recovery; manifolds of fixed-rank matrices appear in maxcut problems and sparse principal component analysis; and oblique manifolds are encountered in problems such as joint diagonalization and blind source separation.
In this talk, I will present an ADMM-like method allowing to handle non-smooth manifold-constrained optimization. Our method is generic and not limited to a specific manifold, is very simple to implement, and does not require parameter tuning. I will show examples of applications from the domains of physics, computer graphics, and machine learning.

03 באפריל 2016, 14:00

חדר 011, בניין כיתות-חשמל

EE Seminar: High Resolution Direct Position Determination of Radio Frequency Sources

~~Speaker: Tom Tirer
M.Sc. student under the supervision of Prof. Anthony J. Weiss

Wednesday, April 6th, 2016 at 15:30
Room 011, Kitot Bldg., Faculty of Engineering

High Resolution Direct Position Determination of Radio Frequency Sources

Abstract

The most common methods for localization of radio frequency transmitters are based on two processing steps. In the first step, parameters such as angle of arrival or time of arrival are estimated at each base station independently. In the second step, the estimated parameters are used to determine the location of the transmitters. The direct position determination approach advocates using the observations from all the base stations together in order to estimate the locations in a single step. This single-step method is known to outperform two-step methods when the signal to noise ratio is low, and inherently overcomes the problem of associating estimated parameters with their relevant sources.
In the presented work, we propose a direct-position-determination-based method for localization of multiple emitters that transmit unknown signals. The method does not require knowledge of the number of emitters, and therefore the use of model order determination techniques is avoided. It is based on minimum-variance-distortionless-response considerations to achieve a high resolution estimator that requires only a two-dimensional search for planar geometry, and a three dimensional search for the general case.
We study two different scenarios. The first scenario is localization of stationary radio emitters using stationary, spatially separated sensor arrays, which is based on delays and angles of arrival. The second scenario is localization of stationary narrowband radio emitters using multiple moving receivers, which is based on Doppler frequency shifts. In both cases the proposed method shows superiority over other competing spectral-based localization methods. Under the assumption of independent, circular, complex Gaussian snapshots, we derive an analytical expression for the estimation mean square error, composed of variance and bias due to finite sample effects and asymptotic bias. We evaluate the performance of the advocated method and verify the usefulness of the theoretical expressions using extensive Monte Carlo simulations.

06 באפריל 2016, 15:30

חדר 011, בניין כיתות-חשמל

EE Seminar: Performance Enhancement of Positioning Systems Using Sources of Opportunity

~~
Speaker: Eilon Regev,
M.Sc. student under the supervision of Prof. Anthony Weiss

Wednesday, April 6, 2016 at 15:00
Room 011, Kitot Bldg., Faculty of Engineering

Performance Enhancement of Positioning Systems Using Sources of Opportunity
Abstract

The importance of the field of positioning has substantially grown in recent years. Alongside military applications, which were the focus for many years, civil and medical applications are in development, as identifying people in smoke-filled structures, search and rescue, the location of objects' logistical needs, intruder identification and the evolving civil application of indoor navigation.

One of the important parameters of positioning systems, regardless of the operating technique, is evaluating system performance. The most important parameter in such an examination is the assessment of positioning accuracy. This paper studies improvement to system performance which can be achieved by adding cooperative Emitters with known locations. Cooperative Emitters of this kind allow improvement of the system's immunity to systematic errors. Systematic error refers to each component correlative between multiple measurements.

This study presents a number of different models of systematic errors. The theoretical analysis of each model is independent from the measurement technique but for practical examination and testing of model simulations, the TOA method was used:
A. A) Multiple Sensors – each sensor performs a number of measurements towards the target. All measurement error consists of two components: random error and systematic error. Adding Cooperative Emitters creates a correlation between the noise component from the target measurement and the noise component from the measurement to the cooperative emitters.
B. B) Single sensor measurements operating in motion – the sensor has a systematic error (random for a single set of measurements). We assume that the systematic error in this case varies slowly in relation to the total time in which the measurement is used for approximating the target location. In this case, we may assume that the error is fixed for all measurements. Adding cooperative emitters, with measurements obtained from the same systematic error, will allow better revaluation of the systematic error component.
C. C) Positioning error of the sensor during measurements – As this model deals with a moving sensor, the systematic error factor stems from the registration sensor positioning inaccuracy at the time of measurement.
D. D) The speed of the signal in medium - this model is particularly suited for sound-wave-based measurements. The speed of the signal depends on the wind speed and direction.
E. E) Multiple targets positioning – this model is equivalent to a model in which the cooperative emitters location is unknown. It examines the effect of pinpointing a number of targets for each measurement when a random error and a systematic error, common to all measurements, occur with the same sensor.
A theoretical development based on Maximum Likelihood estimation is presented for each error model. This is the optimal estimator which achieves Cramer Rao Lower Bound. The aim of this development is to calculate CRLB as a function of system parameters: sensors positioning with respect to the target (system geometry), the number of measurements from each sensor, noise power ratio between random and systematic noise power, and error distribution. This study presents the benefits of using cooperative emitters in accordance to each of these parameters.
The system geometry, affected by the sensors location, cooperative emitter’s location and the target location, is the most difficult parameter to model (due to the multiplicity of degrees of freedom). Nevertheless, in order to get an indication of the connection between the achieved improvement and the system geometry, an approximation was used for TOA method. Such an approximation allows describing the geometry of the system (approximately) as one parameter: the angle in which the sensors are scattered around the target.
In order to verify the correctness of theoretical development for each individual model - positioning simulation is performed, based on TOA. Measurement samples are generated according to the particular error model, and based on those measurements the positioning is executed. This positioning is based on the linear approximation of the distribution density function around the estimated target location. The obtained positioning results and errors are compared with the expected value of theoretical development.
The results of this work provide a tool for testing the feasibility of the addition of cooperative emitters to the system. Viewing the achieved improvement as dependent in each one of the parameters allows designers to test the feasibility of additional cooperative emitters in contrast to other alternatives: increasing the number of measurements, the use of more precise sensors and change to the layout of the sensors – sensor position adjustment during measurements.

06 באפריל 2016, 15:00

חדר 011, בניין כיתות-חשמל

עמודים